modelgrep
I

IBM: Granite 4.1 8B

ibm-granite/granite-4.1-8b

158th smartest of 178Cheaper than 95% of paidToolsJSON
Use via OpenRouter ↗
Intelligence
12.4
158th of 178
Design Elo
Speed
tokens/sec
Latency
first token
Input price
$0.050
15th cheapest
Context
131K
131K max out

How it compares

Smarter than11%
of all ranked models
Cheaper than95%
of all ranked models

Overview

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Benchmarks

independent · via OpenRouter
Artificial Analysis12th percentile
Intelligence Index
12.4
Coding Index
7.3
Agentic Index
10.7
GPQA Diamond
43%
Humanity's Last Exam
4%
SciCode
22%
Tau²-Bench (agentic)
28%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
WandBbf16$0.050$0.100100%

Specifications

Context window131K
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.050/M
ModeratedNo

Granite 4.1 8B FAQ

How much does Granite 4.1 8B cost?

Granite 4.1 8B costs $0.050 per million input tokens and $0.100 per million output tokens via OpenRouter, making it 15th cheapest of 298 paid models.

How smart is Granite 4.1 8B?

Granite 4.1 8B scores 12.4 on the Artificial Analysis Intelligence Index, ranking 158th of 178 benchmarked models, with a GPQA Diamond score of 43%.

What is Granite 4.1 8B's context window?

Granite 4.1 8B supports a 131K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head